Three Major AI PC Disassemblies: Unveiling Core Technologies of 2024 Edge AI Era

Artificial Intelligence (AI) functionality has become essential in various mobile devices. Especially in 2024, AI PCs are being launched into the market, which can even be referred to as the “Edge Device AI Era.” This time, we will review the main AI PCs and processors released in the second half of 2024.

The semiconductor industry in 2024 is expected to be fully led by AI technology. Chips with AI processing capabilities, high-capacity dynamic random-access memory (including high-bandwidth memory and low-power double data rate 5X type) compatible with AI technology, and power integrated circuits capable of executing segmented power management are being integrated into the mobile device field on an unprecedented scale.

With the rapid development of generative AI technology, AI functionality has become standard in devices such as personal computers, smartphones, augmented reality/virtual reality devices, drones, and in-vehicle systems. Some AI systems are combined with cameras and sensors, while others operate in the background to optimize wireless communication environments.

Given the multitude of processors and products about to be released, 2024 can undoubtedly be seen as the “Year of AI Applications for Edge Devices.” Therefore, this article will focus specifically on personal computers and processors equipped with AI technology launched in the second half of 2024.

Three Major Changes Brought by Mobile AI

Mobile AI devices are leading three significant transformations.

First, processors integrate a dedicated hardware computing unit called NPU (Neural Processing Unit), responsible for executing specific integer operations, floating-point operations, and multiply-accumulate operations, which leads to a corresponding increase in chip area.

Secondly, the installation height of parallel large-capacity DRAM matching the computing units has been increased, with major companies adding DRAM capacity in their 2023 models. For example, the “Google Pixel 8” is equipped with 12GB of DRAM (similar examples include the “Google Pixel 9” in 2024, with a capacity of 16GB).

Third, processors are paired with numerous power ICs to achieve fine control over power consumption. With the increase in the number of NPU cores in processors and the expansion of DRAM capacity, power ICs have also been subdivided and increased accordingly. Mobile AI devices are gradually increasing semiconductor usage. In the PC field, models compatible with “Copilot+ PC” (NPU over 40TOPS) will be released as AI PCs starting in June 2024.

Asus AI PC Featuring Qualcomm Snapdragon X

Figure 1 shows the “Vivobook S 15 S5507QA” launched in September 2024, which is compatible with ASUS Copilot+ PC. Its processor is Qualcomm’s “Snapdragon X Plus 8-CORE,” which serves as a budget alternative to the “Snapdragon X Elite,” with performance being a compromise.

This device is equipped with 16GB of DRAM. Given that the market price for high-end laptops typically exceeds 200,000 yen, this product is priced at around 100,000 yen. Although it supports Copilot+ PC, its CPU and GPU performance has been scaled down.

Three Major AI PC Disassemblies: Unveiling Core Technologies of 2024 Edge AI Era

Figure 1: ASUS “Vivobook S 15 S5507QA” released in September 2024

Table 1 reveals the configurations of Qualcomm Snapdragon X Elite (top row) launched in June 2024 and Snapdragon X Plus 8-CORE (bottom row) launched in September. Qualcomm not only provides chipsets for smartphones’ power and communication systems but also offers a diversified range of battery charging, battery management, and power IC products for the personal computer market.

Among these products, there are 8 power ICs and 4 battery ICs. Whether it is the high-end Snapdragon X Elite or the more budget-friendly X Plus 8-CORE, both adopt the same power ICs and battery ICs. This standardized power supply system is also widely used in the smartphone field.

Table 1: Internal configuration of Qualcomm “Snapdragon X” series

Figure 2 shows the Qualcomm Snapdragon X Elite (left) and Snapdragon X Plus 8-CORE (right) chips produced using TSMC’s 4-nanometer process technology. The left X Elite, as a high-end model, is equipped with a 12-core ORYON CPU and a 12-core Qualcomm self-developed GPU Adreno, with a maximum operating frequency of up to 4.3GHz.

Figure 2: Snapdragon X series chips

The right X Plus 8-CORE features a budget central processing unit (CPU) configuration of eight cores, reducing four cores compared to the standard version, while the graphics processing unit (GPU) has seven cores, down five cores. By streamlining functionalities, the chip’s silicon area has been reduced by approximately 28%, and the maximum operating frequency has been adjusted to 4.0GHz.

To meet the performance requirements of Copilot+ PC, the budget version’s Neural Network Processing Unit (NPU) maintains the same performance as the high-end version, at 45TOPS. By reducing the silicon area by about 30%, not only has the amount of data extracted from the wafer increased, but also the reuse of multiple test patterns has significantly reduced production costs, ensuring compatibility with AI PC processors priced in the 100,000 yen range.

HP AI PC Featuring AMD Ryzen

Figure 3 shows the HP OmniBook Ultra 14-fd0005AU launched in July 2024, which is a device compatible with Copilot+ PC. It is equipped with AMD’s APU (Accelerated Processing Unit, a combination of CPU and GPU) – the “Ryzen AI 300” series, designed specifically for Copilot+ PC compatibility.

Compared to the “Ryzen 8000” series APU in 2023, which already integrated AI functionality but failed to meet the performance requirements of Copilot+ PC with only 16TOPS, the Ryzen AI 300 series processors are equipped with up to 50TOPS of performance, with NPU performance increased more than threefold compared to the previous generation. This series of processors began to be integrated into AI personal computers starting in July 2024.

Figure 3: “HP OmniBook Ultra 14-fd0005AU”

Table 2 presents a comparative analysis between the “Ryzen 9 8945HS” processor in the AMD Ryzen APU 8000 series and the “Ryzen AI 300” processor in the Ryzen AI 300 series. It should be noted that AMD has not provided chipset support, and both processors are equipped with MPS (Monolithic Power Systems) power system integrated circuits.

Table 2: Comparison of “Ryzen 9 8945HS” and “Ryzen AI 9 365”

Figure 4 presents a comparative analysis between the Ryzen 9 8945HS and Ryzen AI 300 chips. Both chips include CPU, GPU, and NPU and are manufactured using TSMC’s 4nm process technology. The CPU and GPU architectures of both chips have been upgraded to the latest, with the CPU architecture upgraded from Zen 4 to Zen 5 and the GPU architecture from RDNA3 to RDNA3.5, and the number of cores increased from 12 to 16.

In terms of CPU configuration, a 4-core Zen 5 architecture and an 8-core Zen 5C (compact) architecture have been adopted, with performance streamlined. Because of the same TSMC 4nm process technology, the chip’s functionalities have been enhanced, leading to an approximate 28% increase in silicon area.

It is certain that the next generation of products after 2025 will adopt 3nm process technology, so the 4nm process technology may be the last time it is used, and its size has expanded.

Figure 4: Chip comparison between Ryzen 9 8945HS and Ryzen AI 300

Asus AI PC Featuring Intel Ultra

Figure 5 shows the “Zenbook S 14” (model UX5406) in ASUS’s Copilot+ PC series launched in October 2024. This device is equipped with Intel’s 200V Lunar Lake processor, as the second generation of the “CORE Ultra” series. In comparison, the Meteor Lake launched in January 2024, as the first product of the CORE Ultra series, had an NPU performance of 36TOPS but did not meet the performance requirements of Copilot+ PC. The second generation Lunar Lake processor further enhances NPU performance to 48TOPS, compatible with the performance requirements of Copilot+ PC.

Figure 5: ASUS Copilot+ PC “Zenbook S 14” (UX5406)

Table 3 reveals the chip configurations of personal computers equipped with the first generation Meteor Lake (top row) and the second generation Lunar Lake (bottom row) of the CORE Ultra series. Lunar Lake minimizes chip area and shortens signal transmission distances by integrating DRAM inside the package.

This technology application has been adopted since Apple launched the “M1” chip in 2020, and Apple has actually started using this technology since the “A12X” chip in 2018. As for Meteor Lake, its combined power IC is provided by Alpha & Omega in the United States, while the combined power IC for Lunar Lake is provided by Japan’s Renesas Electronics, totaling four chips.

Table 3: Chip configurations of Meteor Lake and Lunar Lake

Table 4 presents the silicon structures of the first generation Meteor Lake and the second generation Lunar Lake in the CORE Ultra series. Both consist of multiple small chips. Meteor Lake is composed of five different organic silicon materials, including silicon intermediary layers that connect the various chips and provide power.

In contrast, Lunar Lake consists of four organic silicon materials. The CPU of Meteor Lake is manufactured using Intel’s 7-nanometer process (code-named INTEL 4), while its GPU and NPU are outsourced to TSMC. In Lunar Lake, the CPU, GPU, and NPU are all manufactured using TSMC’s 3-nanometer process.

Almost simultaneously, Intel also began launching Arrow Lake processors aimed at desktop computers, which also utilize TSMC’s 3-nanometer process and feature a small chip architecture. It is expected that in the second half of 2024, Copilot+ compatible processors will be launched, but it is worth noting that there are differences among companies in the power ICs used for manufacturing chips.

Table 4: Silicon status of Meteor Lake and Lunar Lake

By 2025, the alliance between MediaTek and NVIDIA is expected to further expand into the Copilot+ PC market. At the same time, Qualcomm, AMD, and Intel also intend to launch their next-generation processor products. We will continue to monitor the smartphone market and provide relevant observations and reports.

Source | Electronic Engineering Album

Recommended Reading——

The United States plans to add 200+ Chinese chip companies to sanctions

The United States adds 13 Chinese companies to the “Unverified List” (with Chinese list attached)

Japan suddenly updates export controls! Including five semiconductor products

Understanding the technical characteristics of the computing power core HBM in one article

The United States upgrades AI chip export ban, 13 Chinese GPU companies listed in the entity list (with list attached)

Another one! Foreign media: The U.S. Department of Commerce will impose export controls on 42 Chinese companies (with Chinese list attached)

The U.S. Department of Commerce again adds 11 Chinese entities to the entity list (with list attached)

Europe and the United States worry about China accelerating the production of traditional chips! Experts: The U.S. government has no clear strategy on chip issues with China

Japan’s advanced semiconductor export control will take effect on July 23, affecting 23 types of manufacturing equipment (with details attached)

Involving nearly 20 Chinese companies! The U.S. Congress investigates four U.S. venture capital companies’ investments in China (with list attached)

The United States announces sanctions against 13 Chinese entities and individuals, and our embassy in the U.S. responds (with a list of sanctioned targets attached)

[Semiconductors] The U.S. adds 12 Chinese companies to the export control “entity list” on the grounds of involving the Russian military

☞ Business Cooperation: ☏ Please call 010-82306118 / ✐ Or send email to [email protected]

Click here to “Read the Original”, go directly to the official website of Electronic Technology Application

Related posts

Leave a Comment Cancel reply